aif-build-automation

Analyze project and generate or enhance build automation file (Makefile, Taskfile.yml, Justfile, Magefile.go). If a build file already exists, improves it by adding missing targets and best practices. Use when user says "generate makefile", "create taskfile", "add justfile", "setup mage", or "build automation".

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete commands, detection patterns, and canonical target names, but it is over-long for the context window and lacks a post-write validation/feedback loop for the destructive build-file write. It also references a templates/ bundle that does not exist in the provided skill.

Suggestions

Consolidate the JVM entrypoint/dev-task logic: it is restated in §2.2, §2.3, and Step 5 — state the predicate once and cross-reference it to remove ~30 lines of repetition.

Add an explicit validate-fix-retry loop after Step 6 writes the file (e.g. run `make -n`/`task --list --dry`/`just --list`/`go vet magefile.go` and re-edit on failure) so destructive write operations have a verification checkpoint, which would lift workflow_clarity to 3.

Move the large Step 5 JVM catalog table and Docker layer blocks into BEST-PRACTICES.md (or a dedicated templates reference) and verify the referenced templates/ directory actually ships with the skill, since progressive_disclosure currently points at a missing bundle path.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient (tables for language/PM/framework detection are tight), but several passages pad with restatement Claude already knows — e.g. the JVM entrypoint predicate is explained three times ("Single source of truth...", "Templates re-resolve at recipe runtime...", and again in Step 5), and the skill-context section repeats the override principle across multiple bullets. It is mostly efficient but could be tightened, matching the score-2 anchor.	2 / 3
Actionability	Guidance is concrete and executable throughout: exact Glob/Grep patterns ("Glob: Makefile, makefile, GNUmakefile, Taskfile.yml..."), precise command tables ("<build_entrypoint> build" / "verify"), canonical target names, and copy-paste-ready Docker layer blocks — matching the score-3 anchor for fully executable, specific examples.	3 / 3
Workflow Clarity	Steps 0–7 are clearly sequenced and the Quality Checks section provides a verification checklist, but there is no validate-then-fix-then-retry feedback loop for the destructive/batch write of the build file: Step 6 writes the file and Step 5's Quality Checks are pre-write self-checks with no post-write verification or rollback. The rubric caps workflow clarity at 2 when validation gaps exist for risky operations.	2 / 3
Progressive Disclosure	The body signals one-level-deep references to real files (BEST-PRACTICES.md, DOC-INTEGRATION.md, SUMMARY-FORMAT.md all exist in references/), but it also references a templates/ directory ("skills/aif-build-automation/templates/<selected-template>") that is absent from the bundle, and large inline catalogs (the Step 5 JVM table, Docker layers) that could live in BEST-PRACTICES.md are kept in the main file. This is some structure with inline content that should be separate — matching the score-2 anchor.	2 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, third-person, and provides both concrete capabilities and explicit "Use when" triggers with natural user phrasing. It cleanly satisfies all four dimensions with no vague language or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Analyze project and generate or enhance build automation file (Makefile, Taskfile.yml, Justfile, Magefile.go)" and "improves it by adding missing targets and best practices" — matching the score-3 anchor that lists several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (generate/enhance build automation files for the four named tools) and when (the "Use when user says..." clause with concrete triggers), satisfying the score-3 anchor for both what AND when.	3 / 3
Trigger Term Quality	Quotes exact user phrases — "generate makefile", "create taskfile", "add justfile", "setup mage", or "build automation" — which are natural terms a user would actually say, giving good coverage per the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	The build-automation niche with tool-specific triggers (makefile/taskfile/justfile/mage) is a clear, distinct scope unlikely to conflict with other skills, matching the score-3 anchor for a clear niche with distinct triggers.	3 / 3
	Total	12 / 12 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (615 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: lee-to/ai-factory
Path: skills/aif-build-automation/SKILL.md
Commit: 4b943ec

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.